{"id":"https://openalex.org/W7108920288","doi":"https://doi.org/10.48550/arxiv.2512.04459","title":"dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning","display_name":"dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning","publication_year":2025,"publication_date":"2025-12-04","ids":{"openalex":"https://openalex.org/W7108920288","doi":"https://doi.org/10.48550/arxiv.2512.04459"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.04459","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.04459","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2512.04459","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Ma, Yingzi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Yingzi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cao, Yulong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Yulong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ding, Wenhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Wenhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Shuibai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Shuibai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ivanovic, Boris","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivanovic, Boris","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiang, Ming","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Pavone, Marco","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pavone, Marco","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xiao, Chaowei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Chaowei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.6811000108718872,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.6811000108718872,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.08780000358819962,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.05139999836683273,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/controllability","display_name":"Controllability","score":0.8666999936103821},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7411999702453613},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6473000049591064},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5932000279426575},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4702000021934509},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4020000100135803},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.35920000076293945}],"concepts":[{"id":"https://openalex.org/C48209547","wikidata":"https://www.wikidata.org/wiki/Q1331104","display_name":"Controllability","level":2,"score":0.8666999936103821},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7411999702453613},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6473000049591064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6353999972343445},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5932000279426575},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4702000021934509},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36559998989105225},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C87833898","wikidata":"https://www.wikidata.org/wiki/Q1060280","display_name":"Advanced driver assistance systems","level":2,"score":0.35429999232292175},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.35030001401901245},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.2856999933719635},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.2793000042438507},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27399998903274536},{"id":"https://openalex.org/C31388003","wikidata":"https://www.wikidata.org/wiki/Q7624548","display_name":"Strong consistency","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.04459","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.04459","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2512.04459","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.04459","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"autonomous":[1],"driving":[2,15,26,151],"community":[3],"is":[4],"increasingly":[5],"focused":[6],"on":[7,112,134,176],"addressing":[8],"the":[9],"challenges":[10],"posed":[11],"by":[12,28,72],"out-of-distribution":[13],"(OOD)":[14],"scenarios.":[16,179],"A":[17],"dominant":[18],"research":[19],"trend":[20],"seeks":[21],"to":[22,41,82,149],"enhance":[23],"end-to-end":[24,131,190],"(E2E)":[25],"systems":[27,153],"integrating":[29],"vision-language":[30,52,120],"models":[31],"(VLMs),":[32],"leveraging":[33],"their":[34],"rich":[35],"world":[36],"knowledge":[37],"and":[38,75,85,90,106,127,136,144,169,185],"reasoning":[39,89],"abilities":[40],"improve":[42],"generalization":[43],"across":[44],"diverse":[45],"environments.":[46],"However,":[47],"most":[48],"existing":[49,67,150],"VLMs":[50,69,98],"or":[51],"agents":[53],"(VLAs)":[54],"are":[55],"built":[56],"upon":[57],"autoregressive":[58],"(AR)":[59],"models.":[60],"In":[61,93],"this":[62],"paper,":[63],"we":[64,115],"observe":[65],"that":[66,122],"AR-based":[68,159],"--":[70,79],"limited":[71],"causal":[73],"attention":[74,102],"sequential":[76],"token":[77],"generation":[78],"often":[80],"fail":[81],"maintain":[83],"consistency":[84,168],"controllability":[86,105],"between":[87],"high-level":[88],"low-level":[91,128],"planning.":[92],"contrast,":[94],"recent":[95],"discrete":[96],"diffusion":[97],"equipped":[99],"with":[100,161],"bidirectional":[101],"exhibit":[103],"superior":[104],"reliability":[107],"through":[108],"iterative":[109],"denoising.":[110],"Building":[111],"these":[113],"observations,":[114],"introduce":[116],"dVLM-AD,":[117],"a":[118,155,162,170,183],"diffusion-based":[119],"model":[121],"unifies":[123],"perception,":[124],"structured":[125],"reasoning,":[126],"planning":[129,146],"for":[130,188],"driving.":[132,191],"Evaluated":[133],"nuScenes":[135],"WOD-E2E,":[137],"dVLM-AD":[138],"yields":[139],"more":[140],"consistent":[141],"reasoning-action":[142],"pairs":[143],"achieves":[145],"performance":[147],"comparable":[148],"VLM/VLA":[152],"despite":[154],"modest":[156],"backbone,":[157],"outperforming":[158],"baselines":[160],"9":[163],"percent":[164,172],"improvement":[165],"in":[166,174],"behavior-trajectory":[167],"6":[171],"increase":[173],"RFS":[175],"long-tail":[177],"WOD-E2E":[178],"These":[180],"results":[181],"suggest":[182],"controllable":[184],"reliable":[186],"pathway":[187],"scalable":[189]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-12-06T00:00:00"}